EXIN CDCS key terms

A purpose-built facility housing IT equipment with controlled power, cooling, connectivity, and physical security, operated to keep systems available and reliable.

The proportion of time a service is actually usable as agreed, usually expressed as a percentage over a defined period, and measured against stated service targets.

The total time a system or facility remains operational and delivering service within a measurement window, contrasted with downtime caused by failures or maintenance.

A four-level scheme describing data center fault tolerance and redundancy, from basic single-path infrastructure to fully fault-tolerant designs with concurrent maintainability.

Duplication of critical components or paths so that a single failure does not interrupt service, often described by the N, N+1, or 2N capacity notation.

Any component or dependency whose failure alone causes loss of service, typically an unprotected path in power, cooling, or network design.

The ability to service, repair, or replace any infrastructure component without shutting down the supported IT load, a defining property of higher-tier facilities.

A pre-agreed period during which planned work may interrupt or degrade service, scheduled and communicated to avoid breaching availability commitments.

A battery-backed device that supplies conditioned power to IT equipment during utility interruptions or disturbances, bridging the gap until generators start or power returns.

Equipment that distributes electrical power to racks or devices, often with metering and switching features that support load monitoring and remote control.

An on-site engine-driven power source that supplies electricity when the utility feed fails, typically starting automatically and carrying load after a short transfer delay.

On-site reserves of diesel or other fuel that determine how long generators can sustain the facility during a prolonged utility outage.

The combination of chillers, air handlers, and airflow design that removes heat from IT equipment and keeps operating temperatures within specified limits.

A rack layout that separates cool supply air from warm exhaust air, improving cooling efficiency and preventing recirculation of heated air into equipment intakes.

A ratio of total facility energy consumption to the energy delivered to IT equipment, used to compare the energy efficiency of data center designs and operations.

A standard frame that holds servers and network equipment, characterized by unit height, power capacity, and cooling provisions.

A service model in which an organization places its own IT equipment in a shared third-party data center that provides space, power, cooling, and physical security.

Controls such as access badges, biometrics, surveillance, and perimeter protection that restrict and record who can reach critical infrastructure and equipment.

The mechanisms and policies that decide who may enter which areas, and that log those entries for audit and investigation.

Detection and extinguishing systems, often using clean agents or inert gas, designed to stop fire without damaging IT equipment or endangering occupants.

The average time needed to restore a failed component or service to normal operation, a key input to availability calculations and maintenance planning.

The capability of a system to continue operating correctly when components fail, achieved through redundancy, detection, and automatic failover mechanisms.

A contract between a provider and a customer that defines measurable service commitments, responsibilities, and remedies when targets are missed.

Documented procedures that keep essential business functions running during and after a disruption, covering people, processes, facilities, and technology dependencies.

A subset of continuity planning focused on restoring IT systems and data after a major disruption, including roles, procedures, and recovery priorities.

The maximum acceptable time to restore a process or system after a disruption, used to design recovery strategies and prioritize resources.

The maximum acceptable amount of data loss measured in time, which drives backup frequency and replication design.

A copy of data kept separately so that it can be restored after loss, corruption, or attack, with schedules and retention governed by recovery objectives.

The practice of forecasting demand for space, power, cooling, and compute so that resources are available before they run short.

A controlled process for assessing, approving, implementing, and reviewing changes to infrastructure or services so that risk and disruption stay acceptable.

Maintaining accurate records of components, their versions, and their relationships, so that changes and incidents can be traced and dependencies understood.

The process of detecting, logging, prioritizing, and resolving service disruptions, restoring normal operation quickly and capturing lessons for prevention.

The discipline of finding and eliminating root causes of recurring incidents, reducing repeat disruption rather than only restoring service each time.

Sensors and alerting for temperature, humidity, water, and airflow that warn of conditions threatening equipment before damage or outage occurs.

A service in which on-site technicians perform physical tasks such as cabling, reboots, or visual checks on behalf of a customer who is not present.

Tracking hardware and other assets through their lifecycle, including location, ownership, configuration, and retirement, to support operations and audits.

Organizing and labeling power and data cabling to preserve airflow, simplify troubleshooting, and prevent accidental disconnection.

Choosing a data center location based on power availability, connectivity, climate, hazard exposure, labor, and regulatory factors that affect risk and cost.

Up-to-date drawings, procedures, and records describing the facility and its operations, essential for safe maintenance, training, and incident response.